Game-theoretic distributed learning of generative models for heterogeneous data collections

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00389618" target="_blank" >RIV/68407700:21230/25:00389618 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/FLLM67465.2025.11391178" target="_blank" >https://doi.org/10.1109/FLLM67465.2025.11391178</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/FLLM67465.2025.11391178" target="_blank" >10.1109/FLLM67465.2025.11391178</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Game-theoretic distributed learning of generative models for heterogeneous data collections

Popis výsledku v původním jazyce

One of the main challenges in distributed learning arises from the difficulty of handling heterogeneous local models and data. In light of the recent success of generative models, we propose to meet this challenge by building on the idea of exchanging synthetic data instead of sharing model parameters. Local models can then be treated as "black boxes" with the ability to learn their parameters from data and to generate data according to these parameters. Moreover, if the local models admit semi-supervised learning, we can extend the approach by enabling local models on different probability spaces. This allows to handle heterogeneous data with different modalities. We formulate the learning of the local models as a cooperative game starting from the principles of game theory. We prove the existence of a unique Nash equilibrium for exponential family local models and show that the proposed learning approach converges to this equilibrium. We demonstrate the advantages of our approach on standard benchmark vision datasets for image classification and conditional generation.

Název v anglickém jazyce

Game-theoretic distributed learning of generative models for heterogeneous data collections

Popis výsledku anglicky

One of the main challenges in distributed learning arises from the difficulty of handling heterogeneous local models and data. In light of the recent success of generative models, we propose to meet this challenge by building on the idea of exchanging synthetic data instead of sharing model parameters. Local models can then be treated as "black boxes" with the ability to learn their parameters from data and to generate data according to these parameters. Moreover, if the local models admit semi-supervised learning, we can extend the approach by enabling local models on different probability spaces. This allows to handle heterogeneous data with different modalities. We formulate the learning of the local models as a cooperative game starting from the principles of game theory. We prove the existence of a unique Nash equilibrium for exponential family local models and show that the proposed learning approach converges to this equilibrium. We demonstrate the advantages of our approach on standard benchmark vision datasets for image classification and conditional generation.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2025 3rd International Conference on Foundation and Large Language Models (FLLM)

ISBN

979-8-3315-9410-7

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

153-160

Název nakladatele

IEEE

Místo vydání

Anchorage, Alaska

Místo konání akce

Vienna

Datum konání akce

25. 11. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—